Great, is there some example for preprocessing the target variable?
Categorical preprocessing layers are a new feature in Keras (available in tf-nightly & TF 2.3). They enable you to do string/int feature encoding directly as part of your model -- one-hot, multi-hot, indexing, hashing, etc. Check out this simple example:https://keras.io/examples/structured_data/structured_data_classification_from_scratch/ …
-
-
-
You could: - Map your preprocessing layer in your http://tf.data pipeline to process the targets - or use the EndpointLayer pattern and make target preprocessing part of the model itself (https://keras.io/examples/keras_recipes/endpoint_layer_pattern/ …)
- Show replies
New conversation -
-
-
Oh that is neat! Makes some things a lot easier.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Very cool!! Need to see if I can connect vtreat (https://github.com/WinVector/vtreat/ …) or some other data preprocessing to deal with all the painful NaNs, nulls, etc. that bite me in real world data...
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This is cool! I particularly liked horizontal plot model. It gives a sense that you're actually feeding in a table input and squashing it to a single number (predicted probability)
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
It’s very explicit, which i like, but quite verbose compared to TF FeatureColumn. I think FeatureColumn is super unintuitive especially when you see it for the first time, and I wonder if there is a middle ground of concise structured input representation and readability?
-
Preprocessing layers are fairly low-level since they expose every step of the preprocessing. You could always write a higher-level, more FeatureColumn-like interface on top. E.g. the `encoder_*` functions in this example are probably close to that: https://keras.io/examples/structured_data/structured_data_classification_from_scratch/#feature-preprocessing-with-keras-layers …
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.